INDEX

Explanations

mentions of comments and interactions in discussions

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

excerpt

-0.08

pron

-0.07

 Sesso

-0.07

íĮ

-0.07

ervoir

-0.07

rowsable

-0.07

_exempt

-0.07

feb

-0.07

kip

-0.07

leck

-0.06

POSITIVE LOGITS

0.07

 below

0.06

 comments

0.06

langs

0.06

CPP

0.06

jin

0.06

0.05

 poll

0.05

 intern

0.05

Activations Density 0.003%